cuda-python: fix module name and version

[ichergui]

This PR fixes #63

Kindly see the logs below

nvidia@tegra-ubuntu:~/cuda-python$ python3 setup.py bdist_wheel --verbose --dist-dir ./dist
Parsing headers in "['/usr/local/cuda-12.4/include']" (Caching False)
Parsing driver headers
Parsing runtime headers
Parsing nvrtc headers
...
running bdist_wheel
running build
running build_py
...
UPDATING build/lib.linux-aarch64-3.10/cuda/_version.py
set build/lib.linux-aarch64-3.10/cuda/_version.py to '12.4.0+0.g2be0aac.dirty'
...
running build_ext
...
adding 'cuda_python-12.4.0+0.g2be0aac.dirty.dist-info/LICENSE'
adding 'cuda_python-12.4.0+0.g2be0aac.dirty.dist-info/METADATA'
adding 'cuda_python-12.4.0+0.g2be0aac.dirty.dist-info/WHEEL'
adding 'cuda_python-12.4.0+0.g2be0aac.dirty.dist-info/top_level.txt'
adding 'cuda_python-12.4.0+0.g2be0aac.dirty.dist-info/RECORD'
removing build/bdist.linux-aarch64/wheel
nvidia@tegra-ubuntu:~/cuda-python$

[ichergui]

• Running a basic tests on the Jetson Orin AGX devkit

  nvidia@tegra-ubuntu:~$ python3
  Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] on linux
  Type "help", "copyright", "credits" or "license" for more information.
  >>> from cuda import cudart
  >>> from cuda import cuda
  >>> cuda_init_result, = cuda.cuInit(0)
  >>> print(cuda_init_result)
  CUresult.CUDA_SUCCESS
  >>> device_count_result, num_devices = cuda.cuDeviceGetCount()
  >>> print (device_count_result)
  CUresult.CUDA_SUCCESS
  >>> print (num_devices)
  1
  >>> property_result, properties = cudart.cudaGetDeviceProperties(0)
  >>> print(property_result)
  cudaError_t.cudaSuccess
  >>> print("Is it Integrated GPU? :", properties.integrated)
  Is it Integrated GPU? : 1
  >>> 
  nvidia@tegra-ubuntu:~$

[ichergui]

Closing this PR since this patch is needed only for OE.